Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 58561
    Prev
    Next
    INDEX
    Explanations

    Alt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     akses
    -0.08
     motivos
    -0.08
     가져
    -0.08
    -0.08
    失败
    -0.08
     خانه
    -0.08
     fearr
    -0.07
     enkelt
    -0.07
     kır
    -0.07
     ir
    -0.07
    POSITIVE LOGITS
    Wonder
    0.09
    encrypt
    0.08
    Wow
    0.08
    Tue
    0.08
    ucin
    0.08
    yň
    0.08
     intim
    0.07
    Wed
    0.07
    Ops
    0.07
    abye
    0.07
    Activations Density 0.000%

    No Known Activations